A method and terminal for detecting abnormal capacity retention rate of electric vehicle battery

The historical capacity retention rate sequence is decomposed through the STL method, the trend terms are extracted and the deviation mean confidence interval is determined, which solves the problem of abnormal detection of battery capacity retention rate of electric vehicles and realizes effective abnormal judgment of real-time capacity retention rate.

CN117368765BActive Publication Date: 2024-11-29CONTEMPORARY NEBULA TECH ENERGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311286803.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-10-07
Publication Date
2024-11-29
Estimated Expiration
2043-10-07

AI Technical Summary

Technical Problem

The prior art is difficult to effectively judge whether there is an abnormality in the capacity retention rate of electric vehicle batteries, which affects the reliability, safety and user satisfaction of electric vehicles.

Method used

The historical capacity retention rate sequence is decomposed by the STL method, the trend term is extracted, and the deviation mean confidence interval is determined based on the sample size, and whether there is an abnormality in the current detected real-time capacity retention rate.

Benefits of technology

It can effectively judge whether there is an abnormality in the current real-time capacity retention rate, which improves the accuracy and reliability of battery detection of electric vehicle.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117368765B_ABST
    Figure CN117368765B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for detecting abnormal capacity retention rate of an electric vehicle battery. The method comprises the following steps: obtaining a historical capacity retention rate sequence of a target vehicle; decomposing the historical capacity retention rate sequence and extracting a trend item through an STL method; determining a deviation mean confidence interval according to a sample size of the historical capacity retention rate sequence; and judging whether a currently detected real-time capacity retention rate is abnormal according to the trend item and the deviation mean confidence interval. The present invention extracts a trend item based on historical detection data through an STL algorithm, and determines a reasonable deviation value based on the historical capacity retention rate sequence, and makes an abnormal judgment according to the reasonable deviation and the trend item, so as to effectively judge whether a currently detected real-time capacity retention rate is abnormal.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal capacity retention rate detection, and in particular to a method and a terminal for abnormal capacity retention rate detection of an electric vehicle battery. Background Art

[0002] With the development of the electric vehicle industry, various testing indicators for electric vehicles are becoming increasingly important. The battery capacity retention rate of electric vehicles is an important battery testing indicator. The battery capacity retention rate refers to the ratio of the effective capacity that can be maintained after a certain charge and discharge cycle to the initial capacity. A high capacity retention rate means a longer battery life and more reliable performance. The identification of abnormal capacity retention rate is of great significance to the reliability, safety and user satisfaction of electric vehicles. Therefore, the detection of abnormal battery capacity retention rate is of great significance to the electric vehicle industry. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and a terminal for detecting abnormal capacity retention rate of an electric vehicle battery, so as to effectively determine whether the capacity retention rate of the currently detected vehicle battery is abnormal.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] A method for detecting abnormal capacity retention rate of an electric vehicle battery, comprising the steps of:

[0006] S1. Obtain the historical capacity retention rate sequence of the target vehicle;

[0007] S2. Decomposing the historical capacity retention rate sequence by STL method and extracting trend items;

[0008] S3. Determine a confidence interval of the mean deviation according to the sample size of the historical capacity retention rate sequence;

[0009] S4. Judging whether the currently detected real-time capacity retention rate is abnormal based on the trend item and the deviation mean confidence interval.

[0010] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0011] A terminal for detecting abnormal capacity retention rate of an electric vehicle battery comprises a processor, a memory and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method for detecting abnormal capacity retention rate of an electric vehicle battery are implemented.

[0012] The beneficial effects of the present invention are as follows: a method and terminal for detecting abnormal capacity retention rate of an electric vehicle battery of the present invention extracts trend items based on historical detection data through an STL algorithm, and determines a reasonable deviation value based on a historical capacity retention rate sequence, and makes an abnormality judgment based on the reasonable deviation and trend item, and can effectively judge whether there is an abnormality in the real-time capacity retention rate currently detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flowchart of a method for detecting abnormal capacity retention rate of an electric vehicle battery according to an embodiment of the present invention;

[0014] Figure 2 This is a structural diagram of a terminal for detecting abnormal capacity retention rate of an electric vehicle battery according to an embodiment of the present invention;

[0015] Figure 3 A schematic diagram of a specific process of a method for detecting abnormal capacity retention rate of an electric vehicle battery according to an embodiment of the present invention;

[0016] Figure 4 An example diagram of the trend of a historical capacity retention rate sequence extracted by an STL algorithm of a method for detecting abnormal capacity retention rate of an electric vehicle battery in an embodiment of the present invention;

[0017] Description of labels:

[0018] 1. A terminal for detecting abnormal capacity retention rate of an electric vehicle battery; 2. A processor; 3. A memory. DETAILED DESCRIPTION

[0019] In order to explain the technical content, achieved objectives and effects of the present invention in detail, the following is an explanation in combination with the implementation modes and the accompanying drawings.

[0020] Please refer to Figure 1 as well as Figure 3 , a method for detecting abnormal capacity retention rate of an electric vehicle battery, comprising the steps of:

[0021] S1. Obtain the historical capacity retention rate sequence of the target vehicle;

[0022] S2. Decomposing the historical capacity retention rate sequence by STL method and extracting trend items;

[0023] S3. Determine a confidence interval of the mean deviation according to the sample size of the historical capacity retention rate sequence;

[0024] S4. Judging whether the currently detected real-time capacity retention rate is abnormal based on the trend item and the deviation mean confidence interval.

[0025] From the above description, it can be seen that the beneficial effects of the present invention are: a method and terminal for detecting abnormal capacity retention rate of an electric vehicle battery of the present invention extract trend items based on historical detection data through the STL algorithm, and determine a reasonable deviation value based on the historical capacity retention rate sequence, and make an abnormality judgment based on the reasonable deviation and trend item, which can effectively judge whether there is an abnormality in the real-time capacity retention rate currently detected.

[0026] Furthermore, the step S3 is specifically as follows:

[0027] Determine whether the sample size of the historical capacity retention rate sequence is greater than or equal to a preset sample size threshold. If so, calculate the deviation mean confidence interval based on the normal distribution z statistic; otherwise, calculate the deviation mean confidence interval based on the t distribution t statistic.

[0028] From the above description, it can be seen that the calculation method of the deviation mean confidence interval is determined according to the sample size, which improves the accuracy of the determination of the deviation mean confidence interval.

[0029] Furthermore, the confidence interval of the deviation mean is calculated based on the normal distribution z statistic as follows:

[0030] For the sample data in the historical capacity retention rate sequence, calculate the sample mean and sample standard deviation s;

[0031] Obtain a preset confidence level, and determine a critical value of the Z statistic according to the confidence level and the sample size;

[0032] Calculate the lower limit LCL and upper limit UCL of the confidence interval:

[0033]

[0034]

[0035] Where Z is the critical value of the Z statistic, n is the sample size, Represents square root.

[0036] From the above description, it can be seen that based on the above steps, the normal distribution z statistic is used to calculate the deviation mean confidence interval.

[0037] Furthermore, the confidence interval of the deviation mean is calculated based on the t-distribution t-statistic as follows:

[0038] For the sample data in the historical capacity retention rate sequence, calculate the sample mean and sample standard deviation s;

[0039] Get the preset confidence level and calculate the degrees of freedom based on the sample size;

[0040] Determining a critical value for finding a t distribution according to the execution level and the degrees of freedom;

[0041] Calculate the lower limit LCL and upper limit UCL of the confidence interval:

[0042]

[0043]

[0044] Where t is the critical value of the t distribution, n is the sample size, Represents square root.

[0045] From the above description, it can be seen that based on the above steps, the deviation mean confidence interval is calculated based on the t-distribution t-statistic.

[0046] Furthermore, step S1 is specifically as follows:

[0047] Obtain all historical inspection data of the target vehicle and extract the historical capacity retention rate information therein.

[0048] It can be seen from the above description that the historical capacity retention rate information is obtained by extracting the historical detection data of the target vehicle.

[0049] Further, step S2 comprises the steps of:

[0050] The historical capacity retention rate sequence is smoothed, the trend of the capacity retention rate and the time series is estimated, and then the capacity retention rate at the current detection time is estimated to obtain a trend item.

[0051] From the above description, it can be seen that the STL method decomposes the historical capacity retention rate sequence, including smoothing the historical capacity retention rate sequence to decompose the capacity retention rate and the trend of the time series, and then determines the capacity retention rate at the current detection time.

[0052] Furthermore, the smoothing process includes moving average processing or exponential smoothing processing.

[0053] As can be seen from the above description, the smoothing process can be performed by moving average processing or exponential smoothing processing.

[0054] Further, step S4 comprises the steps of:

[0055] S41, calculating the deviation value between the currently detected real-time capacity retention rate and the trend item;

[0056] S42: Determine whether the deviation value is within the deviation mean confidence interval; if not, determine that the real-time capacity retention rate is abnormal.

[0057] From the above description, it can be seen that whether there is an abnormality in the real-time capacity retention rate is determined by judging whether the deviation value between the real-time capacity retention rate and the trend item is within the confidence interval of the deviation mean, that is, judging whether the real-time capacity retention rate deviates from the trend development to a large extent.

[0058] Please refer to Figure 2 A terminal for detecting abnormal capacity retention rate of an electric vehicle battery comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned method for detecting abnormal capacity retention rate of an electric vehicle battery when executing the computer program.

[0059] The present invention provides a method and system for detecting abnormality of battery capacity retention rate of an electric vehicle, which is suitable for judging abnormality of detection result of battery capacity retention rate of an electric vehicle.

[0060] Please refer to Figure 1 , Figure 3 and Figure 4 , Embodiment 1 of the present invention is:

[0061] A method for detecting abnormal capacity retention rate of an electric vehicle battery, comprising the steps of:

[0062] S1. Obtain the historical capacity retention rate sequence of the target vehicle;

[0063] Step S1 is specifically as follows:

[0064] Obtain all historical test data of the target vehicle and extract the historical capacity retention rate information. A capacity retention rate can be calculated for each (piece) of historical test data, and multiple capacity retention rates constitute a historical capacity retention rate sequence.

[0065] S2. Decomposing the historical capacity retention rate sequence by STL method and extracting trend items;

[0066] Step S2 comprises the steps of:

[0067] Please refer to Figure 4 , smoothing the historical capacity retention rate sequence, estimating the trend of the capacity retention rate and the time series, and then estimating the capacity retention rate at the current detection time to obtain a trend item;

[0068] The smoothing process includes a moving average process or an exponential smoothing process.

[0069] STL method: STL (Seasonal and Trend decomposition using Loess) decomposition method is a commonly used time series decomposition method, which is used to decompose time series data into three parts: trend, seasonality and residual. The following are the main steps of the STL decomposition method: Seasonal Component: Estimate the seasonal component in the time series through local weighted regression (Loess) or other smoothing techniques. This component represents the periodic fluctuations of the data within a fixed seasonal cycle. Trend Component: Estimate the trend in the time series by smoothing the original data. Commonly used smoothing methods include moving average, exponential smoothing, etc. Residual Component: Subtract the seasonal and trend components from the original data to obtain the remaining part, that is, the residual. The residual reflects the random fluctuations and noise in the data after removing the seasonality and trend.

[0070] S3. Determine a confidence interval of the mean deviation according to the sample size of the historical capacity retention rate sequence;

[0071] The step S3 is specifically as follows:

[0072] Determine whether the sample size of the historical capacity retention rate sequence is greater than or equal to a preset sample size threshold. If so, calculate the deviation mean confidence interval based on the normal distribution z statistic; otherwise, calculate the deviation mean confidence interval based on the t distribution t statistic.

[0073] In this embodiment, the sample size threshold is set to 30. If the sample size is greater than or equal to 30, the mean confidence interval is calculated based on the normal distribution z statistic. If the sample size is less than 30, the mean confidence interval is calculated based on the t distribution t statistic.

[0074] When the distribution of the population is unknown and the sample size is small (n<30), you can use the t-statistic from the t-distribution to calculate a confidence interval for the mean.

[0075] The specific calculation of the deviation mean confidence interval based on the t-distribution t-statistic is:

[0076] For the sample data in the historical capacity retention rate sequence, calculate the sample mean and sample standard deviation s;

[0077] Get a preset confidence level and calculate the degrees of freedom based on the sample size.

[0078] In this example, a 95% confidence level is used, corresponding to α = 0.05. The degree of freedom df is equal to the sample size n minus 1, that is, df = n-1.

[0079] According to the execution level and the degrees of freedom, the critical value of the t distribution is determined. The calculation can be performed using a t distribution table or statistical software.

[0080] Calculate the lower limit LCL and upper limit UCL of the confidence interval:

[0081]

[0082]

[0083] Where t is the critical value of the t distribution, n is the sample size, Represents square root.

[0084] When the sample size is large, the confidence interval for the mean is calculated based on the normal distribution z statistic.

[0085] The confidence interval of the deviation mean is calculated based on the normal distribution z statistic:

[0086] For the sample data in the historical capacity retention rate sequence, calculate the sample mean and sample standard deviation s;

[0087] Obtain a preset confidence level, and determine the critical value of the Z statistic based on the confidence level and the sample size.

[0088] In this embodiment, a 95% confidence level is taken, corresponding to α = 0.05. According to the confidence level and the sample size (n), the critical value of the Z statistic is determined. The critical value of the Z statistic can be found from a standard normal distribution table or calculated using statistical software.

[0089] Calculate the lower limit LCL and upper limit UCL of the confidence interval:

[0090]

[0091]

[0092] Where Z is the critical value of the Z statistic, n is the sample size, Represents square root.

[0093] The resulting confidence interval represents the estimated range of the population mean at a given confidence level. For example, a confidence interval with a 95% confidence level means that there is a 95% confidence that the population mean falls within the interval.

[0094] It should be noted that the above calculation method is based on the assumption that the population conforms to the normal distribution. If the population does not conform to the normal distribution, or the sample size is small, you can consider using other confidence interval calculation methods, such as t distribution.

[0095] S4. judging whether the real-time capacity retention rate currently detected is abnormal according to the trend item and the deviation mean confidence interval;

[0096] Step S4 comprises the steps of:

[0097] S41, calculating the deviation value between the currently detected real-time capacity retention rate and the trend item;

[0098] S42: Determine whether the deviation value is within the deviation mean confidence interval; if not, determine that the real-time capacity retention rate is abnormal.

[0099] If the detected capacity retention rate is determined to be an abnormal value, an abnormal alarm for this indicator is pushed.

[0100] Please refer to Figure 2 , Embodiment 2 of the present invention is:

[0101] A terminal 1 for detecting abnormal capacity retention rate of an electric vehicle battery comprises a processor 2, a memory 3 and a computer program stored in the memory 3 and executable on the processor 2. When the processor 2 executes the computer program, the steps in the above-mentioned method for detecting abnormal capacity retention rate of an electric vehicle battery are implemented.

[0102] In summary, the present invention provides a method and terminal for detecting abnormal capacity retention rate of an electric vehicle battery. The method extracts trend items based on historical detection data through the STL algorithm, and determines a reasonable deviation value based on the historical capacity retention rate sequence. The method performs abnormality judgment based on the reasonable deviation and trend item, and can effectively judge whether there is an abnormality in the real-time capacity retention rate currently detected.

[0103] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting abnormal capacity retention rate of an electric vehicle battery, characterized in that: Includes steps: S1. Obtain the historical capacity retention rate sequence of the target vehicle; S2. Decomposing the historical capacity retention rate sequence by STL method and extracting trend items; S3. Determine a confidence interval of the mean deviation according to the sample size of the historical capacity retention rate sequence; S4. judging whether the real-time capacity retention rate currently detected is abnormal according to the trend item and the deviation mean confidence interval; Step S4 comprises the steps of: S41, calculating the deviation value between the currently detected real-time capacity retention rate and the trend item; S42: Determine whether the deviation value is within the deviation mean confidence interval; if not, determine that the real-time capacity retention rate is abnormal.

2. The method for detecting abnormal capacity retention rate of an electric vehicle battery according to claim 1, characterized in that: The step S3 is specifically as follows: Determine whether the sample size of the historical capacity retention rate sequence is greater than or equal to a preset sample size threshold. If so, calculate the deviation mean confidence interval based on the normal distribution z statistic; otherwise, calculate the deviation mean confidence interval based on the t distribution t statistic.

3. The method for detecting abnormal capacity retention rate of an electric vehicle battery according to claim 2, characterized in that: The confidence interval of the deviation mean is calculated based on the normal distribution z statistic: For the sample data in the historical capacity retention rate sequence, calculate the sample mean and sample standard deviation s; Obtain a preset confidence level, and determine a critical value of the Z statistic according to the confidence level and the sample size; Calculate the lower limit LCL and upper limit UCL of the confidence interval: Where Z is the critical value of the Z statistic, n is the sample size, Represents square root.

4. The method for detecting abnormal capacity retention rate of an electric vehicle battery according to claim 2, characterized in that: The specific calculation of the deviation mean confidence interval based on the t-distribution t-statistic is: For the sample data in the historical capacity retention rate sequence, calculate the sample mean and sample standard deviation s; Get the preset confidence level and calculate the degrees of freedom based on the sample size; Determine a critical value for finding a t distribution according to the confidence level and the degrees of freedom; Calculate the lower limit LCL and upper limit UCL of the confidence interval: Where t is the critical value of the t distribution, n is the sample size, Represents square root.

5. The method for detecting abnormal capacity retention rate of an electric vehicle battery according to claim 1, characterized in that: Step S1 is specifically as follows: Obtain all historical inspection data of the target vehicle and extract the historical capacity retention rate information therein.

6. The method for detecting abnormal capacity retention rate of an electric vehicle battery according to claim 1, characterized in that: Step S2 comprises the steps of: The historical capacity retention rate sequence is smoothed, the trend of the capacity retention rate and the time series is estimated, and then the capacity retention rate at the current detection time is estimated to obtain a trend item.

7. The method for detecting abnormal capacity retention rate of an electric vehicle battery according to claim 6, characterized in that: The smoothing process includes a moving average process or an exponential smoothing process.

8. A terminal for detecting abnormal capacity retention rate of an electric vehicle battery, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps in the method for detecting abnormal capacity retention rate of an electric vehicle battery as described in any one of claims 1 to 7 are implemented.